{"id":"https://openalex.org/W4392859503","doi":"https://doi.org/10.3389/fbinf.2024.1278228","title":"Ten common issues with reference sequence databases and how to mitigate them","display_name":"Ten common issues with reference sequence databases and how to mitigate them","publication_year":2024,"publication_date":"2024-03-15","ids":{"openalex":"https://openalex.org/W4392859503","doi":"https://doi.org/10.3389/fbinf.2024.1278228","pmid":"https://pubmed.ncbi.nlm.nih.gov/38560517"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2024.1278228","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2024.1278228","pdf_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2024.1278228/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2024.1278228/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058688337","display_name":"Samuel D. Chorlton","orcid":"https://orcid.org/0000-0001-9891-8546"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Samuel D. Chorlton","raw_affiliation_strings":["BugSeq Bioinformatics Inc., Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"BugSeq Bioinformatics Inc., Vancouver, BC, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058688337"],"corresponding_institution_ids":[],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":13.9069,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.99411106,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"4","issue":null,"first_page":"1278228","last_page":"1278228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.8877376317977905},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6133209466934204},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5607664585113525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5340996980667114},{"id":"https://openalex.org/keywords/reference-database","display_name":"Reference database","score":0.46314024925231934},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4044307470321655},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3684425354003906},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3615225851535797},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23348677158355713},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07258269190788269}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8877376317977905},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6133209466934204},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5607664585113525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5340996980667114},{"id":"https://openalex.org/C2984717058","wikidata":"https://www.wikidata.org/wiki/Q1789476","display_name":"Reference database","level":2,"score":0.46314024925231934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4044307470321655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3684425354003906},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3615225851535797},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23348677158355713},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07258269190788269},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2024.1278228","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2024.1278228","pdf_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2024.1278228/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38560517","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38560517","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10978663","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10978663","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10978663/pdf/fbinf-04-1278228.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Bioinform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:e6e42704de844a4590c00cff2457f5f8","is_oa":true,"landing_page_url":"https://doaj.org/article/e6e42704de844a4590c00cff2457f5f8","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 4 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2024.1278228","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2024.1278228","pdf_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2024.1278228/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392859503.pdf"},"referenced_works_count":108,"referenced_works":["https://openalex.org/W1482198677","https://openalex.org/W1927467936","https://openalex.org/W1939004772","https://openalex.org/W1968339870","https://openalex.org/W1973862547","https://openalex.org/W1983345777","https://openalex.org/W1985423799","https://openalex.org/W1998330439","https://openalex.org/W2007135806","https://openalex.org/W2015509339","https://openalex.org/W2034285706","https://openalex.org/W2042690128","https://openalex.org/W2059323820","https://openalex.org/W2069982854","https://openalex.org/W2087310128","https://openalex.org/W2107772251","https://openalex.org/W2112364185","https://openalex.org/W2124927293","https://openalex.org/W2130669817","https://openalex.org/W2137662380","https://openalex.org/W2142678478","https://openalex.org/W2143788241","https://openalex.org/W2145946085","https://openalex.org/W2152375430","https://openalex.org/W2159008215","https://openalex.org/W2173732482","https://openalex.org/W2202810729","https://openalex.org/W2347171910","https://openalex.org/W2605606775","https://openalex.org/W2745006471","https://openalex.org/W2758705200","https://openalex.org/W2766485474","https://openalex.org/W2766648240","https://openalex.org/W2767473479","https://openalex.org/W2786358949","https://openalex.org/W2789843538","https://openalex.org/W2797413896","https://openalex.org/W2804906140","https://openalex.org/W2809850832","https://openalex.org/W2881827384","https://openalex.org/W2897603717","https://openalex.org/W2904384071","https://openalex.org/W2941338699","https://openalex.org/W2944602870","https://openalex.org/W2950962479","https://openalex.org/W2950964375","https://openalex.org/W2951160681","https://openalex.org/W2951816104","https://openalex.org/W2953008890","https://openalex.org/W2953263404","https://openalex.org/W2962840130","https://openalex.org/W2963839877","https://openalex.org/W2968450569","https://openalex.org/W2990618091","https://openalex.org/W2998367142","https://openalex.org/W3001118548","https://openalex.org/W3005642314","https://openalex.org/W3012861870","https://openalex.org/W3019706413","https://openalex.org/W3028050938","https://openalex.org/W3033804865","https://openalex.org/W3036067368","https://openalex.org/W3043424179","https://openalex.org/W3044260906","https://openalex.org/W3048090444","https://openalex.org/W3083864964","https://openalex.org/W3088477225","https://openalex.org/W3088602524","https://openalex.org/W3092832969","https://openalex.org/W3093218166","https://openalex.org/W3118048495","https://openalex.org/W3131982567","https://openalex.org/W3138971169","https://openalex.org/W3158909845","https://openalex.org/W3168040031","https://openalex.org/W3174809557","https://openalex.org/W3186309583","https://openalex.org/W3193020855","https://openalex.org/W3198151896","https://openalex.org/W3200103613","https://openalex.org/W3208696114","https://openalex.org/W3209314503","https://openalex.org/W4211037082","https://openalex.org/W4211107894","https://openalex.org/W4213316818","https://openalex.org/W4213454339","https://openalex.org/W4220964817","https://openalex.org/W4221049201","https://openalex.org/W4225399233","https://openalex.org/W4283809266","https://openalex.org/W4307342856","https://openalex.org/W4313261720","https://openalex.org/W4317438868","https://openalex.org/W4319317140","https://openalex.org/W4321611856","https://openalex.org/W4322494209","https://openalex.org/W4323036397","https://openalex.org/W4366286156","https://openalex.org/W4376609018","https://openalex.org/W4379522996","https://openalex.org/W4385580247","https://openalex.org/W4387079708","https://openalex.org/W4387257147","https://openalex.org/W4387440002","https://openalex.org/W4392358871","https://openalex.org/W6810037007","https://openalex.org/W6854933902","https://openalex.org/W6891286447"],"related_works":["https://openalex.org/W2582197062","https://openalex.org/W4245864934","https://openalex.org/W2373861055","https://openalex.org/W2325136493","https://openalex.org/W1988339775","https://openalex.org/W3092657713","https://openalex.org/W2334394689","https://openalex.org/W4255512368","https://openalex.org/W4243839507","https://openalex.org/W1600150098"],"abstract_inverted_index":{"Metagenomic":[0],"sequencing":[1],"has":[2,22],"revolutionized":[3],"our":[4],"understanding":[5],"of":[6,93],"microbiology.":[7],"While":[8],"metagenomic":[9,32,122],"tools":[10,105],"and":[11,17,71,74,88,106,120],"approaches":[12],"have":[13],"been":[14,23],"extensively":[15],"evaluated":[16],"benchmarked,":[18],"far":[19],"less":[20],"attention":[21],"given":[24],"to":[25],"the":[26,44,49,89],"reference":[27,36,63,85],"sequence":[28,37,64,75,86],"database":[29,107],"used":[30],"in":[31,48,56],"classification.":[33],"Issues":[34],"with":[35,62,84],"databases":[38,65,87],"are":[39,98],"pervasive.":[40],"Database":[41],"contamination":[42],"is":[43],"most":[45,57],"recognized":[46],"issue":[47],"literature;":[50],"however,":[51],"it":[52],"remains":[53],"relatively":[54],"unmitigated":[55],"analyses.":[58],"Other":[59],"common":[60,82],"issues":[61,83],"include":[66],"taxonomic":[67],"errors,":[68],"inappropriate":[69],"inclusion":[70],"exclusion":[72],"criteria,":[73],"content":[76],"errors.":[77],"This":[78],"review":[79],"covers":[80],"ten":[81],"potential":[90],"downstream":[91],"consequences":[92],"these":[94,111],"issues.":[95],"Mitigation":[96],"measures":[97],"discussed":[99],"for":[100],"each":[101],"issue,":[102],"including":[103],"bioinformatic":[104],"curation":[108],"strategies.":[109],"Together,":[110],"strategies":[112],"present":[113],"a":[114],"path":[115],"towards":[116],"more":[117],"accurate,":[118],"reproducible":[119],"translatable":[121],"sequencing.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}